Matching pursuit
From Wikipedia, the free encyclopedia
Matching pursuit is a type of numerical technique which involves finding the "best matching" projections of multidimensional data onto an over-complete basis.
The concept of matching pursuit was inspired by projection pursuit, in which "interesting" projections were found; ones that deviate more from a normal distribution are considered to be more interesting.
 |
This statistics-related article is a stub. You can help Wikipedia by expanding it. |
[edit] References
1. S. G. Mallat and Z. Zhang, Matching Pursuits with Time-Frequency Dictionaries , IEEE Transactions on Signal Processing, December 1993, pp. 3397-3415.
2. S. E. Ferrando and L. A. Kolasa, "Algorithm 820: A Flexible implementation of matching pursuit for Gabor functions on the interval," ACM Trans. mathematical software, Vol. 28, No. 3, Sep. 2002, pp. 337-353.
